High-performance Machine Learning Model Research Articles

Combining ChatGPT and knowledge graph for explainable machine learning-driven design: a case study

Machine learning has been widely used in design activities, enabling more informed decision-making. However, high-performance machine learning models, often referred to as ‘black-box', result in a lack of explainability regarding predictions. The absence of explainability erodes the trust between designers and these models and hinders human-machine collaboration for desirable design decisions. Explainable AI focuses on creating explanations that are accessible and comprehensible to stakeholders, thereby improving explainability. A recent advancement in the field of explainable AI involves leveraging domain-specific knowledge via knowledge graph. Additionally, the advent of large language models like ChatGPT, acclaimed for their ability to output domain knowledge, perform complex language processing, and support seamless end-user interaction, has the potential to expand the horizons of explainable AI. Inspired by these developments, we propose the novel hybrid method that synergizes ChatGPT and knowledge graph to augment post-hoc explainability in design context. The outcome is the generation of more contextual and meaningful explanations, with the added possibility of further interaction to uncover deeper insights. The effectiveness of the proposed method is illustrated through a case study on customer segmentation.

Privacy-preserving culvert predictive models: A federated learning approach

In recent years, transportation agencies have shown a growing interest in the adoption of machine learning (ML) models as a means to improve the efficiency of their infrastructure asset management practices. Their limited inventory can, however, hinder the development of robust ML models. Moreover, transportation agencies may be reluctant to share their raw inventory data with others. To address these challenges, we employed a new ML paradigm, federated learning (FL), and demonstrated its potential in the case study of Utah culvert management. The Utah Department of Transportation (UDOT) only owned a limited culvert inventory, but we were able to obtain additional data from five other state DOTs’ inventories. Rather than employing a conventional centralized ML method, we opted for FL. This approach ensured that while UDOT did not directly access raw data from five other DOTs, it could still benefit from their combined insights. The FL-based model with 80.4 % accuracy showed a promising performance between the two centralized learning models developed based on the consolidated and the Utah-only datasets. The federated approach demonstrates that it is possible to develop high-performance ML models without compromising data confidentiality by centralizing data. This pioneering approach sets a precedent for other transportation agencies, suggesting they can navigate data scarcity and privacy concerns while reaping the benefits of collective knowledge.

Machine Learning Algorithms for Predictive Maintenance in Industrial Environments: A Comparative Study

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases.
 
 While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications

Security Challenges of Vehicular Cloud Computing

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases. While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications.

Machine Learning Algorithms for Predictive Maintenance in Industrial Environments: A Comparative Study

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases. While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications.

Security Challenges of Vehicular Cloud Computing

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases.
 
 While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications.

AutoSR4EO: An AutoML Approach to Super-Resolution for Earth Observation Images

Super-resolution (SR), a technique to increase the resolution of images, is a pre-processing step in the pipelines of applications of Earth observation (EO) data. The manual design and optimisation of SR models that are specific to every possible EO use case is a laborious process that creates a bottleneck for EO analysis. In this work, we develop an automated machine learning (AutoML) method to automate the creation of dataset-specific SR models. AutoML is the study of the automatic design of high-performance machine learning models. We present the following contributions. (i) We propose AutoSR4EO, an AutoML method for automatically constructing neural networks for SR. We design a search space based on state-of-the-art residual neural networks for SR and incorporate transfer learning. Our search space is extendable, making it possible to adapt AutoSR4EO to future developments in the field. (ii) We introduce a new real-world single-image SR (SISR) dataset, called SENT-NICFI. (iii) We evaluate the performance of AutoSR4EO on four different datasets against the performance of four state-of-the-art baselines and a vanilla AutoML SR method, with AutoSR4EO achieving the highest average ranking. Our results show that AutoSR4EO performs consistently well over all datasets, demonstrating that AutoML is a promising method for improving SR techniques for EO images.

TiFLCS-MARP: Client selection and model pricing for federated learning in data markets

In recent years, the burgeoning data market has witnessed a surge in data exchange, playing a pivotal role in augmenting the predictive and decision-making capabilities of machine learning. Despite these advancements, persistent concerns surrounding data privacy have resulted in stringent limitations on data sharing and trading. Consequently, the data market is undergoing a transformative shift from pricing individual datasets to pricing the models themselves. The challenge of training high-performance machine learning models with restricted data from a single client is substantial. Federated learning has emerged as a popular solution, allowing collaborative model training without the need to transfer client data beyond local environments. However, training federated models within a data market introduces several challenges, including the effective selection of clients for model training and the optimization of utility through model pricing. In response to these challenges, we propose the Tiered Federated Learning Client Selection Algorithm (TiFLCS-MAR), employing a multi-attribute reverse auction approach. Integrated into the federated learning framework, TiFLCS-MAR excels at the comprehensive evaluation of client attributes, employing a tiered strategy to mitigate issues arising from client heterogeneity. Additionally, we introduce the TiFLCS-MAR Pricing Framework (TiFLCS-MARP), leveraging Nash equilibrium principles to maximize profitability for both clients and servers. Our framework accommodates the heterogeneity of diverse clients, efficiently selecting suitable candidates from a large pool, thereby boosting training efficiency and curbing model pricing costs. Empirical evidence showcases the efficacy of federated training with TiFLCS-MAR, demonstrating nearly double the convergence speed and a 5-10 percentage point improvement in accuracy across real and synthetic datasets. Furthermore, when compared to three baseline algorithms, TiFLCS-MARP substantially increases central server revenue by factors of 1.99, 27.05, and 1.78, highlighting its superior performance in the data market context.

Evaluating the Performance of Automated Machine Learning (AutoML) Tools for Heart Disease Diagnosis and Prediction

Globally, over 17 million people annually die from cardiovascular diseases, with heart disease being the leading cause of mortality in the United States. The ever-increasing volume of data related to heart disease opens up possibilities for employing machine learning (ML) techniques in diagnosing and predicting heart conditions. While applying ML demands a certain level of computer science expertise—often a barrier for healthcare professionals—automated machine learning (AutoML) tools significantly lower this barrier. They enable users to construct the most effective ML models without in-depth technical knowledge. Despite their potential, there has been a lack of research comparing the performance of different AutoML tools on heart disease data. Addressing this gap, our study evaluates three AutoML tools—PyCaret, AutoGluon, and AutoKeras—against three datasets (Cleveland, Hungarian, and a combined dataset). To evaluate the efficacy of AutoML against conventional machine learning methodologies, we crafted ten machine learning models using the standard practices of exploratory data analysis (EDA), data cleansing, feature engineering, and others, utilizing the sklearn library. Our toolkit included an array of models—logistic regression, support vector machines, decision trees, random forest, and various ensemble models. Employing 5-fold cross-validation, these traditionally developed models demonstrated accuracy rates spanning from 55% to 60%. This performance is markedly inferior to that of AutoML tools, indicating the latter’s superior capability in generating predictive models. Among AutoML tools, AutoGluon emerged as the superior tool, consistently achieving accuracy rates between 78% and 86% across the datasets. PyCaret’s performance varied, with accuracy rates from 65% to 83%, indicating a dependency on the nature of the dataset. AutoKeras showed the most fluctuation in performance, with accuracies ranging from 54% to 83%. Our findings suggest that AutoML tools can simplify the generation of robust ML models that potentially surpass those crafted through traditional ML methodologies. However, we must also consider the limitations of AutoML tools and explore strategies to overcome them. The successful deployment of high-performance ML models designed via AutoML could revolutionize the treatment and prevention of heart disease globally, significantly impacting patient care.

Association between PM2.5 exposure and the outcomes of ART treatment: A prospective birth cohort study

Exposure to fine particulate matter (PM2.5) has been reported to be adversely associated with reproductive health. However, current evidence on PM2.5 exposure adversely influencing pregnancy outcomes remains inconclusive. Women receiving assisted reproductive technology (ART) treatment are under close monitoring with regards to their treatment process, which make them great study population to assess the impact of PM2.5 in the post-implantation period. Therefore, within a prospective cohort study in Jiangsu, China, we assessed the associations between exposure to ambient PM2.5 and the outcomes of ART treatment, including implantation failure, biochemical pregnancy loss, clinical pregnancy and live birth, in 2431 women who underwent the first fresh embryo transfer or frozen embryo transfer cycle. High-performance machine-learning model was performed to estimate daily PM2.5 exposure concentrations at 1 km spatial revolution. Exposure windows were divided into seven periods according to the process of follicular and embryonic development in ART. Generalized estimation equations (GEE) was used to assess the association between PM2.5 and ART outcomes. Higher PM2.5 exposure was associated with decreased probability of clinical pregnancy (RR: 0.98, 95 % CI: 0.96–1.00). Each 10 μg/m3 increase in PM2.5 exposure in the duration from hCG test to 30 days after embryo transfer (Period 7) was positively associated with the risk of biochemical pregnancy loss (RR: 1.06, 95 % CI: 1.00–1.13), and more prominent effects were observed in women undergoing fresh embryo transfer. Null associations were observed between PM2.5 exposure and implantation failure or live birth at any exposure window. Collectively, our study suggested that exposure to PM2.5 increased the risk of adverse treatment outcomes in the ART population. Thus, for women opting for ART treatment, particularly those who select fresh embryo transfer cycles, additional evaluation of PM2.5 exposure before treatment might be of value in decreasing the risk of adverse pregnancy outcomes.

Firing-rate-modulated spike detection and neural decoding co-design

Objective. Translational efforts on spike-signal-based implantable brain-machine interfaces (BMIs) are increasingly aiming to minimise bandwidth while maintaining decoding performance. Developing these BMIs requires advances in neuroscience and electronic technology, as well as using low-complexity spike detection algorithms and high-performance machine learning models. While some state-of-the-art BMI systems jointly design spike detection algorithms and machine learning models, it remains unclear how the detection performance affects decoding. Approach. We propose the co-design of the neural decoder with an ultra-low complexity spike detection algorithm. The detection algorithm is designed to attain a target firing rate, which the decoder uses to modulate the input features preserving statistical invariance in long term (over several months). Main results. We demonstrate a multiplication-free fixed-point spike detection algorithm with an average detection accuracy of 97% across different noise levels on a synthetic dataset and the lowest hardware complexity among studies we have seen. By co-designing the system to incorporate statistically invariant features, we observe significantly improved long-term stability, with decoding accuracy degrading by less than 10% after 80 days of operation. Our analysis also reveals a nonlinear relationship between spike detection and decoding performance. Increasing the detection sensitivity improves decoding accuracy and long-term stability, which means the activity of more neurons is beneficial despite the detection of more noise. Reducing the spike detection sensitivity still provides acceptable decoding accuracy whilst reducing the bandwidth by at least 30%. Significance. Our findings regarding the relationship between spike detection and decoding performance can provide guidance on setting the threshold for spike detection rather than relying on training or trial-and-error. The trade-off between data bandwidth and decoding performance can be effectively managed using appropriate spike detection settings. We demonstrate improved decoding performance by maintaining statistical invariance of input features. We believe this approach can motivate further research focused on improving decoding performance through the manipulation of data itself (based on a hypothesis) rather than using more complex decoding models.

Evaluation of a Machine Learning Approach for Temperature Prediction in Pavement Base and Subgrade Layers in Alberta, Canada

The performance of flexible pavement is influenced by pavement material properties and the strength or the stiffness of the pavement layers. Pavement temperature significantly impacts the material properties of flexible pavements. However, to date there has not been much research that investigates the prediction of the pavement temperature in unbound material (base and subgrade layers). The goal of this research is to apply a new approach, machine learning, to predict pavement temperature in unbound material. Pavement temperature recordings collected at the Integrated Road Research Facility (IRRF) test road in Alberta from January 2013 to February 2020 were used to train and validate machine learning models. Finally, high-performance machine learning models with two parameters (air temperature and day of the year) were developed to predict the average daily pavement temperature at 0.5–2.7 m below the road surface. The accuracy of the temperature in the base and subgrade layers predicted using the machine learning models was found to be higher than for an existing model.

Prenatal exposure to fine particulate matter and newborn anogenital distance: a prospective cohort study

BackgroundConsiderable attention has been paid to reproductive toxicity of fine particulate matter (PM2.5). However, the relationship between prenatal PM2.5 exposure and anogenital distance (AGD) has not been well studied. We aim to investigate the potential effects of prenatal exposure to PM2.5 on newborn AGD.MethodsPrenatal PM2.5 exposure of 2332 participates in Shanghai (2013–2016) was estimated using high-performance machine learning models. Anoscrotal distance (AGDas) in male infants and anofourchette distance (AGDaf) in female infants were measured by well-trained examiners within 3 days after birth. We applied multiple linear regression models and multiple informant models to estimate the association between prenatal PM2.5 exposure and AGD.ResultsMultiple linear regression models showed that a 10 μg/m3 increase in PM2.5 exposure during full pregnancy, the second and third trimesters was inversely associated with AGDas (adjusted beta = − 1.76, 95% CI: − 2.21, − 1.31; − 0.73, 95% CI: − 1.06, − 0.40; and − 0.52; 95% CI: − 0.87, − 0.18, respectively) in males. A 10 μg/m3 increase in PM2.5 exposure during the full pregnancy, the first, second, and third trimesters was inversely associated with AGDaf (adjusted beta = − 4.55; 95% CI: − 5.18, − 3.92; − 0.78; 95% CI: − 1.10, − 0.46; − 1.11; 95% CI: − 1.46, − 0.77; − 1.45; 95% CI: − 1.78, − 1.12, respectively) in females after adjusting for potential confounders. Multiple informant models showed consistent but slightly attenuated associations.ConclusionOur study observed a significant association between gestational PM2.5 exposure during pregnancy and shortened AGD in newborns, and provided new evidence on potential reproductive toxicity of prenatal PM2.5 exposure.

COVID19PREDICTOR: KLİNİK VERİLERE VE RUTİN TESTLERE DAYALI OLARAK COVID-19 TEŞHİSİ İÇİN MAKİNE ÖĞRENİMİ MODELLERİ GELİŞTİRMEYE YARAYAN WEB TABANLI ARAYÜZ

Objective: The Covid-19 outbreak has become the primary health problem of many countries due to health related, social, economic and individual effects. In addition to the development of outbreak prediction models, the examination of risk factors of the disease and the development of models for diagnosis are of high importance. This study introduces the Covid19PredictoR interface, a workflow where machine learning approaches are used for diagnosing Covid-19 based on clinical data such as routine laboratory test results, risk factors, information on co-existing health conditions.
 Method: Covid19PredictoR interface is an open source web based interface on R/Shiny (https://biodatalab.shinyapps.io/Covid19PredictoR/). Logistic regression, C5.0, decision tree, random forest and XGBoost models can be developed within the framework. These models can also be used for predictive purposes. Descriptive statistics, data pre-processing and model tuning steps are additionally provided during model development.
 Results: Einsteindata4u dataset was analyzed with the Covid19PredictoR interface. With this example, the complete operation of the interface and the demonstration of all steps of the workflow have been shown. High performance machine learning models were developed for the dataset and the best models were used for prediction. Analysis and visualization of features (age, admission data and laboratory tests) were carried out for the case per model.
 Conclusion: The use of machine learning algorithms to evaluate Covid-19 disease in terms of related risk factors is rapidly increasing. The application of these algorithms on various platforms creates application difficulties, repeatability and reproducibility problems. The proposed pipeline, which has been transformed into a standard workflow with the interface, offers a user-friendly structure that healthcare professionals with various background can easily use and report.

Modelling and Forecasting of EUR/USD Exchange Rate Using Ensemble Learning Approach

Abstract The aim of the study is to obtain an accurate result from forecasting the EUR/USD exchange rate. To this end, high-performance machine learning models using CART Ensembles and Bagging method have been developed. Key macroeconomic indicators have been also examined including inflation in Europe and the United States, the index of unemployment in Europe and the United States, and more. Official monthly data in the period from December 1998 to December 2021 have been studied. A careful analysis of the macroeconomic time series has shown that their lagged variables are suitable for model’s predictors. CART Ensembles and Bagging predictive models having been built, explaining up to 98.8% of the data with MAPE of 1%. The degree of influence of the considered macroeconomic indicators on the EUR/USD rate has been established. The models have been used for forecasting one-month-ahead. The proposed approach could find a practical application in professional trading, budgeting and currency risk hedging.

Feature extraction from MRI ADC images for brain tumor classification using machine learning techniques

BackgroundDiffusion-weighted (DW) imaging is a well-recognized magnetic resonance imaging (MRI) technique that is being routinely used in brain examinations in modern clinical radiology practices. This study focuses on extracting demographic and texture features from MRI Apparent Diffusion Coefficient (ADC) images of human brain tumors, identifying the distribution patterns of each feature and applying Machine Learning (ML) techniques to differentiate malignant from benign brain tumors.MethodsThis prospective study was carried out using 1599 labeled MRI brain ADC image slices, 995 malignant, 604 benign from 195 patients who were radiologically diagnosed and histopathologically confirmed as brain tumor patients. The demographics, mean pixel values, skewness, kurtosis, features of Grey Level Co-occurrence Matrix (GLCM), mean, variance, energy, entropy, contrast, homogeneity, correlation, prominence and shade, were extracted from MRI ADC images of each patient. At the feature selection phase, the validity of the extracted features were measured using ANOVA f-test. Then, these features were used as input to several Machine Learning classification algorithms and the respective models were assessed.ResultsAccording to the results of ANOVA f-test feature selection process, two attributes: skewness (3.34) and GLCM homogeneity (3.45) scored the lowest ANOVA f-test scores. Therefore, both features were excluded in continuation of the experiment. From the different tested ML algorithms, the Random Forest classifier was chosen to build the final ML model, since it presented the highest accuracy. The final model was able to predict malignant and benign neoplasms with an 90.41% accuracy after the hyper parameter tuning process.ConclusionsThis study concludes that the above mentioned features (except skewness and GLCM homogeneity) are informative to identify and differentiate malignant from benign brain tumors. Moreover, they enable the development of a high-performance ML model that has the ability to assist in the decision-making steps of brain tumor diagnosis process, prior to attempting invasive diagnostic procedures, such as brain biopsies.

A novel integrated approach of augmented grey wolf optimizer and ANN for estimating axial load carrying-capacity of concrete-filled steel tube columns

The purpose of this study is to offer a high-performance machine learning model for determining the ultimate load-carrying capability of concrete-filled steel tube (CFST) columns. The proposed approach is a novel hybrid machine learning model that combines artificial neural network (ANN) and augmented grey wolf optimizer (AGWO). AGWO is a simple and effective augmentation to the conventional grey wolf optimizer (GWO). In addition to AGWO, an enhanced version of grey wolf optimizer (EGWO) was employed in this study, and two hybrid models, namely ANN-AGWO and ANN-EGWO were created for estimating the load-carrying capacity of CFST columns. The suggested hybrid models were evaluated on two distinct datasets with a variety of input combinations. The proposed ANN-AGWO achieved the most precise prediction during the testing phase, outperforming support vector regression, extreme learning machine, group data handling method, and other hybrid ANNs constructed using particle swarm optimization, grey wolf optimizer, salp swarm algorithm, slime mould algorithm, and Harris hawks optimization algorithms. Based on the experimental findings, the suggested ANN-AGWO can be utilized as a high-performance tool to estimate the load-carrying capacity of CFST columns during the design and preparatory stages of civil engineering projects.

Understanding the Role of the Microbiome in Cancer Diagnostics and Therapeutics by Creating and Utilizing ML Models

Recent studies have highlighted that gut microbiota can alter colorectal cancer susceptibility and progression due to its impact on colorectal carcinogenesis. This work represents a comprehensive technical approach in modeling and interpreting the drug-resistance mechanisms from clinical data for patients diagnosed with colorectal cancer. To accomplish our aim, we developed a methodology based on evaluating high-performance machine learning models where a Python-based random forest classifier provides the best performance metrics, with an overall accuracy of 91.7%. Our approach identified and interpreted the most significant genera in the cases of resistant groups. Thus far, many studies point out the importance of present genera in the microbiome and intend to treat it separately. The symbiotic bacterial analysis generated different sets of joint feature combinations, providing a combined overview of the model’s predictiveness and uncovering additional data correlations where different genera joint impacts support the therapy-resistant effect. This study points out the different perspectives of treatment since our aggregate analysis gives precise results for the genera that are often found together in a resistant group of patients, meaning that resistance is not due to the presence of one pathogenic genus in the patient microbiome, but rather several bacterial genera that live in symbiosis.

Designing clinically translatable artificial intelligence systems for high-dimensional medical imaging

The National Institutes of Health in 2018 identified key focus areas for the future of artificial intelligence in medical imaging, creating a foundational roadmap for research in image acquisition, algorithms, data standardization and translatable clinical decision support systems. Among the key issues raised in the report, data availability, the need for novel computing architectures and explainable artificial intelligence algorithms are still relevant, despite the tremendous progress made over the past few years alone. Furthermore, translational goals of data sharing, validation of performance for regulatory approval, generalizability and mitigation of unintended bias must be accounted for early in the development process. In this Perspective, we explore challenges unique to high-dimensional clinical imaging data, in addition to highlighting some of the technical and ethical considerations involved in developing machine learning systems that better represent the high-dimensional nature of many imaging modalities. Furthermore, we argue that methods that attempt to address explainability, uncertainty and bias should be treated as core components of any clinical machine learning system. Substantial advances have been made in the past decade in developing high-performance machine learning models for medical applications, but translating them into practical clinical decision-making processes remains challenging. This Perspective provides insights into a range of challenges specific to high-dimensional, multimodal medical imaging.

A novel integrated approach of ELM and modified equilibrium optimizer for predicting soil compression index of subgrade layer of Dedicated Freight Corridor

This study proposes a high-performance machine learning model to sidestep the time of conducting actual laboratory tests of soil compression index (Cc), one of the important criteria for determining the settlement of subgrade layers of roadways, railways, and airport runways. The suggested method combines the modified equilibrium optimizer (MEO) and the extreme learning machine (ELM) in a novel way. In this study, Gaussian mutation with an exploratory search mechanism was incorporated to construct the MEO and used to enhance the performance of conventional ELM by optimizing its learning parameters. PCA (Principal component analysis)-based results exhibit that the developed ELM-MEO attained the most precise prediction with R2 = 0.9746, MAE = 0.0184, and RMSE = 0.0284 in training, and R2 = 0.9599, MAE = 0.0232, and RMSE = 0.0357 in the testing phase. The results showed that the proposed ELM-MEO model outperformed the other developed models, confirming the ELM-MEO model's superiority over the other models, such as random forest, gradient boosting machine, genetic programming, including the ELM and artificial neural network (ANN)-based models optimized with equilibrium optimizer, particle swarm optimization, Harris hawks optimization, slime mould algorithm, and marine predators algorithm. Based on the experimental results, the proposed ELM-MEO can be used as a promising alternative to predict soil Cc in civil engineering projects, including rail and road projects.